Top

European Journal of Nuclear Medicine and Molecular Imaging

Published in:

Open Access 20-05-2022 | Artificial Intelligence | Original Article

Artificial intelligence-based PET denoising could allow a two-fold reduction in [¹⁸F]FDG PET acquisition time in digital PET/CT

Authors: Kathleen Weyts, Charline Lasnon, Renaud Ciappuccini, Justine Lequesne, Aurélien Corroyer-Dulmont, Elske Quak, Bénédicte Clarisse, Laurent Roussel, Stéphane Bardet, Cyril Jaudet

Published in: European Journal of Nuclear Medicine and Molecular Imaging | Issue 11/2022

Abstract

Purpose

We investigated whether artificial intelligence (AI)-based denoising halves PET acquisition time in digital PET/CT.

Methods

One hundred ninety-five patients referred for [¹⁸F]FDG PET/CT were prospectively included. Body PET acquisitions were performed in list mode. Original “PET90” (90 s/bed position) was compared to reconstructed ½-duration PET (45 s/bed position) with and without AI-denoising, “PET45AI and PET45”. Denoising was performed by SubtlePET™ using deep convolutional neural networks. Visual global image quality (IQ) 3-point scores and lesion detectability were evaluated. Lesion maximal and peak standardized uptake values using lean body mass (SUL_max and SUL_peak), metabolic volumes (MV), and liver SUL_mean were measured, including both standard and EARL₁ (European Association of Nuclear Medicine Research Ltd) compliant SUL. Lesion-to-liver SUL ratios (LLR) and liver coefficients of variation (CV_liv) were calculated.

Results

PET45 showed mediocre IQ (scored poor in 8% and moderate in 68%) and lesion concordance rate with PET90 (88.7%). In PET45AI, IQ scores were similar to PET90 (P = 0.80), good in 92% and moderate in 8% for both. The lesion concordance rate between PET90 and PET45AI was 836/856 (97.7%), with 7 lesions (0.8%) only detected in PET90 and 13 (1.5%) exclusively in PET45AI. Lesion EARL₁ SUL_peak was not significantly different between both PET (P = 0.09). Lesion standard SUL_peak, standard and EARL1 SUL_max, LLR and CV_liv were lower in PET45AI than in PET90 (P < 0.0001), while lesion MV and liver SUL_mean were higher (P < 0.0001). Good to excellent intraclass correlation coefficients (ICC) between PET90 and PET45AI were observed for lesion SUL and MV (ICC ≥ 0.97) and for liver SUL_mean (ICC ≥ 0.87).

Conclusion

AI allows [¹⁸F]FDG PET duration in digital PET/CT to be halved, while restoring degraded ½-duration PET image quality. Future multicentric studies, including other PET radiopharmaceuticals, are warranted.

Available only for authorised users

Conti M, Bendriem B. The new opportunities for high time resolution clinical TOF PET. Clinical and Translational Imaging Springer. 2019;7:139–47. https://doi.org/10.1007/s40336-019-00316-5.CrossRef

Rausch I, Ruiz A, Valverde-Pascual I, Cal-González J, Beyer T, Carrio I. Performance evaluation of the Vereos PET/CT system according to the NEMA NU2–2012 standard. Journal of Nuclear Medicine. Soc Nuclear Med; 2019;60:561–7. https://doi.org/10.2967/jnumed.118.215541

Zhang J, Maniawski P, Knopp MV. Performance evaluation of the next generation solid-state digital photon counting PET/CT system. EJNMMI Res. 2018;8:97. https://doi.org/10.1186/s13550-018-0448-7.CrossRefPubMedPubMedCentral

Salvadori J, Odille F, Verger A, Olivier P, Karcher G, Marie P-Y, et al. Head-to-head comparison between digital and analog PET of human and phantom images when optimized for maximizing the signal-to-noise ratio from small lesions. EJNMMI Phys. 2020;7:11. https://doi.org/10.1186/s40658-020-0281-8.CrossRefPubMedPubMedCentral

López-Mora DA, Carrió I, Flotats A. Digital PET vs analog PET: clinical implications? Seminars in Nuclear Medicine. Elsevier. 2021. https://doi.org/10.1053/j.semnuclmed.2021.10.004.CrossRef

Nensa F, Demircioglu A, Rischpler C. Artificial intelligence in nuclear medicine. J Nucl Med. 2019;60:29S-37S. https://doi.org/10.2967/jnumed.118.220590.CrossRefPubMed

Seifert R, Weber M, Kocakavuk E, Rischpler C, Kersting D. Artificial intelligence and machine learning in nuclear medicine: future perspectives. Semin Nucl Med. 2021;51:170–7. https://doi.org/10.1053/j.semnuclmed.2020.08.003.CrossRefPubMed

Hong X, Zan Y, Weng F, Tao W, Peng Q, Huang Q. Enhancing the image quality via transferred deep residual learning of coarse PET sinograms. IEEE transactions on medical imaging IEEE. 2018;37:2322–32. https://doi.org/10.1109/TMI.2018.2830381.CrossRef

Kim K, Wu D, Gong K, Dutta J, Kim JH, Son YD, et al. Penalized PET reconstruction using deep learning prior and local linear fitting. IEEE transactions on medical imaging IEEE. 2018;37:1478–87. https://doi.org/10.1109/TMI.2018.2832613.CrossRef

10.

Cui J, Gong K, Guo N, Wu C, Meng X, Kim K, et al. PET image denoising using unsupervised deep learning. European journal of nuclear medicine and molecular imaging. Springer; 2019;46:2780–. https://doi.org/10.1007/s00259-019-04468-4

11.

Berg E, Cherry SR. Using convolutional neural networks to estimate time-of-flight from PET detector waveforms. Physics in Medicine & Biology. IOP Publishing; 2018;63:02LT01. https://doi.org/10.1088/1361-6560/aa9dc5

12.

Liu J, Malekzadeh M, Mirian N, Song T-A, Liu C, Dutta J. Artificial intelligence-based image enhancement in PET imaging: noise reduction and resolution enhancement. PET clinics Elsevier. 2021;16:553–76. https://doi.org/10.1016/j.cpet2021.06.005.CrossRef

13.

Kaplan S, Zhu Y-M. Full-dose PET image estimation from low-dose PET image using deep learning: a pilot study. Journal of digital imaging Springer. 2019;32:773–8. https://doi.org/10.1007/s10278-018-0150-3.CrossRef

14.

Xiang L, Qiao Y, Nie D, An L, Lin W, Wang Q, et al. Deep auto-context convolutional neural networks for standard-dose PET image estimation from low-dose PET/MRI. Neurocomputing Elsevier. 2017;267:406–16. https://doi.org/10.1016/j.neucom.2017.06.048.CrossRef

15.

Schaefferkoetter J, Yan J, Ortega C, Sertic A, Lechtman E, Eshet Y, et al. Convolutional neural networks for improving image quality with noisy PET data. EJNMMI research Springer. 2020;10:1–11. https://doi.org/10.1186/s13550-020-00695-1.CrossRef

16.

Sanaat A, Shiri I, Arabi H, Mainta I, Nkoulou R, Zaidi H. Deep learning-assisted ultra-fast/low-dose whole-body PET/CT imaging. Eur J Nucl Med Mol Imaging. 2021;48:2405–15. https://doi.org/10.1007/s00259-020-05167-1.CrossRefPubMedPubMedCentral

17.

Zhou L, Schaefferkoetter JD, Tham IW, Huang G, Yan J. Supervised learning with cyclegan for low-dose FDG PET image denoising. Medical Image Analysis. Elsevier; 2020;65:101770. https://doi.org/10.1016/j.media.2020.101770

18.

Liu H, Wu J, Lu W, Onofrey JA, Liu Y-H, Liu C. Noise reduction with cross-tracer and cross-protocol deep transfer learning for low-dose PET. Phys Med Biol. 2020;65: 185006. https://doi.org/10.1088/1361-6560/abae08.CrossRefPubMed

19.

Lu W, Onofrey JA, Lu Y, Shi L, Ma T, Liu Y, et al. An investigation of quantitative accuracy for deep learning based denoising in oncological PET. Physics in Medicine & Biology. IOP Publishing; 2019;64:165019. https://doi.org/10.1088/1361-6560/ab3242

20.

Wang Y-RJ, Baratto L, Hawk KE, Theruvath AJ, Pribnow A, Thakor AS, et al. Artificial intelligence enables whole-body positron emission tomography scans with minimal radiation exposure. Eur J Nucl Med Mol Imaging. 2021. https://doi.org/10.1007/s00259-021-05197-3

21.

Mehranian A, Wollenweber SD, Walker MD, Bradley KM, Fielding PA, Su K-H, et al. Image enhancement of whole-body oncology [18F]-FDG PET scans using deep neural networks to reduce noise. European Journal of Nuclear Medicine and Molecular Imaging. Springer; 2021;1–11. https://doi.org/10.1007/s00259-021-05478-x

22.

SubtlePET | Subtle Medical [Internet]. accessed on Nov 17 2021. Available from: https://subtlemedical.com/subtlepet/

23.

Sahiner B, Pezeshk A, Hadjiiski LM, Wang X, Drukker K, Cha KH, et al. Deep learning in medical imaging and radiation therapy. Med Phys. 2019;46:e1-36. https://doi.org/10.1002/mp.13264.CrossRefPubMed

24.

LeCun Y, Kavukcuoglu K, Farabet C. Convolutional networks and applications in vision. Proceedings of 2010 IEEE international symposium on circuits and systems. IEEE. 2010; https://doi.org/10.1109/ISCAS.2010.5537907

25.

Katsari K, Penna D, Arena V, Polverari G, Ianniello A, Italiano D, et al. Artificial intelligence for reduced dose 18F-FDG PET examinations: a real-world deployment through a standardized framework and business case assessment. EJNMMI Phys. 2021;8:25. https://doi.org/10.1186/s40658-021-00374-7.CrossRefPubMedPubMedCentral

26.

Chaudhari AS, Mittra E, Davidzon GA, Gulaka P, Gandhi H, Brown A, et al. Low-count whole-body PET with deep learning in a multicenter and externally validated study. NPJ digital medicine Nature Publishing Group. 2021;4:1–11. https://doi.org/10.1038/s41746-021-00497-2.CrossRef

27.

Jaudet C, Weyts K, Lechervy A, Batalla A, Bardet S, Corroyer-Dulmont A. The impact of artificial intelligence CNN based denoising on FDG PET radiomics. Frontiers in oncology. Frontiers; 2021;3136. https://doi.org/10.3389/fonc.2021.692973

28.

Boellaard R, Delgado-Bolton R, Oyen WJG, Giammarile F, Tatsch K, Eschner W, et al. FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging. 2015;42:328–54. https://doi.org/10.1007/s00259-014-2961-x

29.

Janmahasatian S, Duffull SB, Ash S, Ward LC, Byrne NM, Green B. Quantification of lean bodyweight. Clinical pharmacokinetics Springer. 2005;44:1051–65. https://doi.org/10.2165/00003088-200544100-00004.CrossRef

30.

Quak E, Le Roux P-Y, Hofman MS, Robin P, Bourhis D, Callahan J, et al. Harmonizing FDG PET quantification while maintaining optimal lesion detection: prospective multicentre validation in 517 oncology patients. Eur J Nucl Med Mol Imaging. 2015;42:2072–82. https://doi.org/10.1007/s00259-015-3128-0.CrossRefPubMedPubMedCentral

31.

Aide N, Lasnon C, Veit-Haibach P, Sera T, Sattler B, Boellaard R. EANM/EARL harmonization strategies in PET quantification: from daily practice to multicentre oncological studies. Eur J Nucl Med Mol Imaging. 2017;44:17–31. https://doi.org/10.1007/s00259-017-3740-2.CrossRefPubMedPubMedCentral

32.

Koo TK, Li MY. Cracking the code: providing insight into the fundamentals of research and evidence-based practice a guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med. 2016;15:155–63. https://doi.org/10.1016/j.jcm.2016.02.012.CrossRefPubMedPubMedCentral

33.

Mawlawi O, Jordan D, Halama J, Schmidtlein C, Wooten W. PET/CT acceptance testing and quality assurance [Internet]. AAPM; 2019 Oct. Available from: https://www.aapm.org/pubs/reports/detail.asp?docid=193

34.

Wahl RL, Jacene H, Kasamon Y, Lodge MA. From RECIST to PERCIST: evolving considerations for PET response criteria in solid tumors. Journal of nuclear medicine. Soc Nuclear Med; 2009;50:122S-150S. https://doi.org/10.2967/jnumed.108.057307

35.

Joo Hyun O, Lodge MA, Wahl RL. Practical PERCIST: a simplified guide to PET response criteria in solid tumors 1.0. radiology. Radiological Society of North America; 2016;280:576. https://doi.org/10.1148/radiol.2016142043

36.

Kaalep A, Sera T, Rijnsdorp S, Yaqub M, Talsma A, Lodge MA, et al. Feasibility of state of the art PET/CT systems performance harmonisation. European journal of nuclear medicine and molecular imaging. Springer; 2018;45:1344–61. https://doi.org/10.1007/s00259-018-3977-4

Title: Artificial intelligence-based PET denoising could allow a two-fold reduction in [18F]FDG PET acquisition time in digital PET/CT
Authors: Kathleen Weyts
Charline Lasnon
Renaud Ciappuccini
Justine Lequesne
Aurélien Corroyer-Dulmont
Elske Quak
Bénédicte Clarisse
Laurent Roussel
Stéphane Bardet
Cyril Jaudet
Publication date: 20-05-2022
Publisher: Springer Berlin Heidelberg
Keyword: Artificial Intelligence
Published in: European Journal of Nuclear Medicine and Molecular Imaging / Issue 11/2022
Print ISSN: 1619-7070
Electronic ISSN: 1619-7089
DOI: https://doi.org/10.1007/s00259-022-05800-1

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Artificial intelligence-based PET denoising could allow a two-fold reduction in [¹⁸F]FDG PET acquisition time in digital PET/CT

Abstract

Purpose

Methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 11/2022

Hepatocellular carcinoma radiation segmentectomy treatment intensification prior to liver transplantation increases rates of complete pathologic necrosis: an explant analysis of 75 tumors

Letter to the editor regarding “Bone metastases from differentiated thyroid carcinoma: heterogenous tumor response to radioactive Iodine therapy and overall survival”

Spatial density and tumor dosimetry are important in radiation segmentectomy with 90Y glass microspheres

Imaging joint infections using D-methyl-11C-methionine PET/MRI: initial experience in humans

Monoamine oxidase binding not expected to significantly affect [18F]flortaucipir PET interpretation

Fibrin-targeting molecular MRI in inflammatory CNS disorders